Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    sexual context, code, math, programming, data, objectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     translucent
    0.52
     endearing
    0.49
     γ
    0.49
     semi
    0.48
     eccentric
    0.48
     goats
    0.47
     mitochondria
    0.47
     Old
    0.46
    amię
    0.46
     niektó
    0.46
    POSITIVE LOGITS
     देखता
    0.51
    For
    0.47
    Middleware
    0.46
    OUR
    0.46
    EX
    0.46
    Karena
    0.46
    Forever
    0.46
    Trying
    0.45
    Whilst
    0.45
    ាទ
    0.45
    Act Density 0.000%

    No Known Activations